A Fast Feature Extraction Algorithm for Detection of Foreign Fiber in Lint Cotton within a Complex Background

Abstract A novel algorithm is presented in this paper to extract the features of foreign fibers in lint cotton within a complex background. The 2D wavelet transform is used to implement the edge detection based on the gray contrast between foreign fibers and cotton background, while the color features are extracted in CrCgCb color cube to solve the problem of luminance fluctuation. Morphological analysis is a critical procedure of the algorithm and the discontinuity of object features and operation time must be considered. Therefore, the proposed approach integrates a two-level connected component labeling algorithm and a morphological identification algorithm based on equivalent length-width ratio. Tests on five typical kinds of foreign fibers were implemented, and the results show that the identification rate of the above-mentioned algorithm is about 95 %. The experimental results demonstrate that the feature extraction algorithm can identify foreign fibers effectively and can be used in real-time application.

[1]  Liang Kun,et al.  Key Technology in Detecting and Eliminating Isomerism Fibre in Cotton , 2007, 2007 8th International Conference on Electronic Measurement and Instruments.

[2]  Wei Gao.  Robust and Efficient Cotton Contamination Detection Method Based on HSI Color Space: Robust and Efficient Cotton Contamination Detection Method Based on HSI Color Space , 2009 .

[3]  B. Xu,et al.  Clustering Analysis for Cotton Trash Classification , 1999 .

[4]  Gao Wei.  Robust and Efficient Cotton Contamination Detection Method Based on HSI Color Space , 2008 .

[5]  Zhang Xiu.  The Pixel Labeled Algorithm with Label Rectified of Connecting Area in Binary Pictures , 2003 .

[6]  Wei XinHua,et al.  Toward image segmentation of foreign fibers in lint. , 2009 .

[7]  Jin Shou-fen,et al.  Cotton foreign fiber detection and orientation arithmetic based on Matlab , 2004 .

[8]  Narciso García,et al.  Face detection based on a new color space YCgCr , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[9]  Gordon F. Williams,et al.  Evolution of the Microdust and Trash Monitor for Cotton Classification , 1986 .

[10]  Anil K. Jain,et al.  A Survey of Automated Visual Inspection , 1995, Comput. Vis. Image Underst..

[11]  Ai Shi-yi.  On-line measuring for unusual-fine in raw cotton based on image-recognition technology with MATLAB , 2004 .

[12]  Abbas Dehghani,et al.  Real-time automated visual inspection system for contaminant removal from wool , 2005, Real Time Imaging.

[13]  Nadipuram R. Prasad,et al.  Identification of trash types and computation of trash content in ginned cotton using soft computing techniques , 1999, 42nd Midwest Symposium on Circuits and Systems (Cat. No.99CH36356).